35 citations · 97 across the 15 of their papers we have counts for
15 papers
Collaborative Multi-Teacher Knowledge Distillation for Learning Low Bit-width Deep Neural Networks
Cuong Pham, Tuan Hoang, Thanh-Toan Do
Knowledge distillation which learns a lightweight student model by distilling knowledge from a cumbersome teacher model is an attractive approach for learning compact deep neural n…
Multi-Modal Mutual Information Maximization: A Novel Approach for Unsupervised Deep Cross-Modal Hashing
Tuan Hoang, Thanh-Toan Do, Tam V. Nguyen +1
In this paper, we adopt the maximizing mutual information (MI) approach to tackle the problem of unsupervised learning of binary hash codes for efficient cross-modal retrieval. We…
Unsupervised Deep Cross-modality Spectral Hashing
Tuan Hoang, Thanh-Toan Do, Tam V. Nguyen +1
This paper presents a novel framework, namely Deep Cross-modality Spectral Hashing (DCSH), to tackle the unsupervised learning problem of binary hash codes for efficient cross-moda…
BTEL: A Binary Tree Encoding Approach for Visual Localization
Huu Le, Tuan Hoang, Michael Milford
Visual localization algorithms have achieved significant improvements in performance thanks to recent advances in camera technology and vision-based techniques. However, there rema…
Simultaneous Feature Aggregating and Hashing for Compact Binary Code Learning
Thanh-Toan Do, Khoa Le, Tuan Hoang +3
Representing images by compact hash codes is an attractive approach for large-scale content-based image retrieval. In most state-of-the-art hashing-based image retrieval systems, f…
A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning
Thanh-Toan Do, Toan Tran, Ian Reid +3
We propose a method that substantially improves the efficiency of deep distance metric learning based on the optimization of the triplet loss function. One epoch of such training p…
SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration without Correspondences
Huu Le, Thanh-Toan Do, Tuan Hoang +1
This paper presents a novel randomized algorithm for robust point cloud registration without correspondences. Most existing registration approaches require a set of putative corres…
SASSE: Scalable and Adaptable 6-DOF Pose Estimation
Huu Le, Tuan Hoang, Qianggong Zhang +3
Visual localization has become a key enabling component of many place recognition and SLAM systems. Contemporary research has primarily focused on improving accuracy and precision-…
Binary Constrained Deep Hashing Network for Image Retrieval without Manual Annotation
Thanh-Toan Do, Tuan Hoang, Dang-Khoa Le Tan +4
Learning compact binary codes for image retrieval task using deep neural networks has attracted increasing attention recently. However, training deep hashing networks for the task…
Simultaneous Compression and Quantization: A Joint Approach for Efficient Unsupervised Hashing
Tuan Hoang, Thanh-Toan Do, Huu Le +2
For unsupervised data-dependent hashing, the two most important requirements are to preserve similarity in the low-dimensional feature space and to minimize the binary quantization…
From Selective Deep Convolutional Features to Compact Binary Representations for Image Retrieval
Thanh-Toan Do, Tuan Hoang, Dang-Khoa Le Tan +3
In the large-scale image retrieval task, the two most important requirements are the discriminability of image representations and the efficiency in computation and storage of repr…
Compact Hash Code Learning with Binary Deep Neural Network
Thanh-Toan Do, Tuan Hoang, Dang-Khoa Le Tan +2
Learning compact binary codes for image retrieval problem using deep neural networks has recently attracted increasing attention. However, training deep hashing networks is challen…
Accessible Melanoma Detection using Smartphones and Mobile Image Analysis
T. -T. Do, T. Hoang, V. Pomponiu +6
We investigate the design of an entire mobile imaging system for early detection of melanoma. Different from previous work, we focus on smartphone-captured visible light images. Ou…
Selective Deep Convolutional Features for Image Retrieval
Tuan Hoang, Thanh-Toan Do, Dang-Khoa Le Tan +1
Convolutional Neural Network (CNN) is a very powerful approach to extract discriminative local descriptors for effective image search. Recent work adopts fine-tuned strategies to f…
Enhance Feature Discrimination for Unsupervised Hashing
Tuan Hoang, Thanh-Toan Do, Dang-Khoa Le Tan +1
We introduce a novel approach to improve unsupervised hashing. Specifically, we propose a very efficient embedding method: Gaussian Mixture Model embedding (Gemb). The proposed met…